Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3173 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6287. Min Act: -0.0000

Data Index: 651749 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6637. Min Act: -0.0000

Data Index: 698828 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6001. Min Act: -0.0000

Data Index: 46536 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5412. Min Act: -0.0000

Data Index: 323127 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1256961 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1090907 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1325063 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5631. Min Act: -0.0000

Data Index: 777693 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1163832 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5166. Min Act: -0.0000

Data Index: 565743 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5128. Min Act: -0.0000

Data Index: 336254 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1335554 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4965. Min Act: -0.0000

Data Index: 134820 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1067332 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1122725 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4801. Min Act: -0.0000

Data Index: 220747 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4634. Min Act: -0.0000

Data Index: 74241 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4790. Min Act: -0.0000

Data Index: 937329 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1287957 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4726. Min Act: -0.0000

Data Index: 457228 (C4 (Web Text))

Max Activating Token Index: 329